LATIDIA · Investigación

Un Marco de Evaluación Unificado para Modelos de Lenguaje Grande Confiables, IA Agénica y Sistemas Multimodales

arXiv: 2609.19524v1Tipo de anuncio: nuevo Resumen: Las puntuaciones de referencia por sí solas proporcionan una base incompleta para evaluar la confiabilidad de los sistemas modernos de inteligencia artificial. Modelos de lenguaje grandes (LLM), sistema agentic

La noticia

arXiv:2609.19524v1 Announce Type: new Abstract: Benchmark scores alone provide an incomplete basis for assessing the trustworthiness of modern artificial intelligence systems. Large language models (LLMs), agentic systems, and multimodal models (MLLMs) require different forms of assessment, yet their evaluation evidence must remain interpretable for development and oversight. We propose a unified framework that connects output-level, trajectory-level, and cross-modal assessment through eight trustworthiness dimensions: capability, robustness, safety, fairness, transparency, governance, oversight, and efficiency. The framework preserves system-specific metrics while mapping native measurements to common performance bands, accompanied by uncertainty estimates and traceable evidence. A meta-evaluation layer examines the validity, reliability, and reproducibility of the evaluation itself. Multidimensional profiles expose strengths and